AI agents call list_knowledge_bases to retrieve information from Yunxiao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
page | number | — | Page number for pagination. Starts at 1. |
sort | string | — | Sort order: desc or asc. |
query | string | — | Knowledge base name fuzzy query. |
userId | string | — | User ID permission filter. |
orderBy | string | — | Sort field. |
perPage | number | — | Page size for pagination. Supports 1-100. Defaults to 20 when omitted. |
sceneType | string | — | Scene type, such as chat or completion. |
organizationId | string | — | Yunxiao organization ID. When omitted, the server uses the user's default organization. |
Parameters from the server's own tool schema.
This tool retrieves or queries metadata about knowledge bases within an organization. It has no side effects, does not execute code or commands, does not modify data, and does not delete anything. The operation is purely informational (list/read).
From the tool's definition Tool name is 'list_knowledge_bases' and description states it 'List[s] Tongyi Lingma knowledge bases' — a query operation with no modification or execution semantics. Knowledge bases are data containers; listing them is a retrieval operation.
Attacks that exploit this kind of access
List Tongyi Lingma knowledge bases in a Yunxiao organization. Knowledge bases contain curated documents for AI-assisted code completion and chat. It is categorised as a Read tool in the Yunxiao MCP Server, which means it retrieves data without modifying state.
list_knowledge_bases accepts 8 parameters: page, sort, query, userId, orderBy, perPage, sceneType, organizationId. The full parameter table on this page comes from the server's own tool schema.
Register the Yunxiao MCP server in PolicyLayer and add a rule for list_knowledge_bases: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yunxiao. Nothing to install.
list_knowledge_bases is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_knowledge_bases rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_knowledge_bases. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_knowledge_bases is provided by the Yunxiao MCP server (@futuretea/yunxiao-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →